{"id":"https://openalex.org/W4415536373","doi":"https://doi.org/10.1145/3746027.3758150","title":"MLLMs Meet Person Re-identification","display_name":"MLLMs Meet Person Re-identification","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536373","doi":"https://doi.org/10.1145/3746027.3758150"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3758150","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3758150","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120131205","display_name":"Mengying Duan","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengying Duan","raw_affiliation_strings":["School of Computer Science, Wuhan University, Wuhan, Hubei, China"],"raw_orcid":"https://orcid.org/0009-0009-8068-0838","affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101292336","display_name":"Li He","orcid":"https://orcid.org/0000-0002-8469-8260"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He Li","raw_affiliation_strings":["School of Computer Science, Wuhan University, Wuhan, Hubei, China"],"raw_orcid":"https://orcid.org/0000-0002-8469-8260","affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008999954","display_name":"Mang Ye","orcid":"https://orcid.org/0000-0003-3989-7655"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mang Ye","raw_affiliation_strings":["School of Computer Science, Wuhan University, Wuhan, Hubei, China"],"raw_orcid":"https://orcid.org/0000-0003-3989-7655","affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12247","last_page":"12256"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9871000051498413,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7569000124931335},{"id":"https://openalex.org/keywords/biometrics","display_name":"Biometrics","score":0.5382999777793884},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4246000051498413},{"id":"https://openalex.org/keywords/iris-recognition","display_name":"Iris recognition","score":0.4246000051498413},{"id":"https://openalex.org/keywords/clothing","display_name":"Clothing","score":0.37470000982284546},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.3192000091075897}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7569000124931335},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7071999907493591},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5687999725341797},{"id":"https://openalex.org/C184297639","wikidata":"https://www.wikidata.org/wiki/Q177765","display_name":"Biometrics","level":2,"score":0.5382999777793884},{"id":"https://openalex.org/C112356035","wikidata":"https://www.wikidata.org/wiki/Q1672722","display_name":"Iris recognition","level":3,"score":0.4246000051498413},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4246000051498413},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39590001106262207},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39070001244544983},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38659998774528503},{"id":"https://openalex.org/C530175646","wikidata":"https://www.wikidata.org/wiki/Q11460","display_name":"Clothing","level":2,"score":0.37470000982284546},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.3192000091075897},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C2776694159","wikidata":"https://www.wikidata.org/wiki/Q351676","display_name":"Viewing angle","level":3,"score":0.299699991941452},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C2780027415","wikidata":"https://www.wikidata.org/wiki/Q524648","display_name":"Language change","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.26030001044273376}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3758150","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3758150","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5212831058","display_name":null,"funder_award_id":"62176188, 62361166629, 62476188","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1965301261","https://openalex.org/W2018507448","https://openalex.org/W2204750386","https://openalex.org/W2213726222","https://openalex.org/W2228002889","https://openalex.org/W2586899202","https://openalex.org/W2798794112","https://openalex.org/W2963047834","https://openalex.org/W2981576453","https://openalex.org/W2994675267","https://openalex.org/W2998792609","https://openalex.org/W3034727830","https://openalex.org/W4304084033","https://openalex.org/W4382240158","https://openalex.org/W4385301128","https://openalex.org/W4386076164","https://openalex.org/W4388099806","https://openalex.org/W4390606904","https://openalex.org/W4392158419","https://openalex.org/W4401387006","https://openalex.org/W4402916438","https://openalex.org/W4402917263","https://openalex.org/W4403052637","https://openalex.org/W4403148853","https://openalex.org/W4403210636","https://openalex.org/W4404239149","https://openalex.org/W4407376583","https://openalex.org/W4409365953"],"related_works":[],"abstract_inverted_index":{"Person":[0],"re-identification":[1],"(Re-ID)":[2],"models":[3],"have":[4],"achieved":[5],"remarkable":[6],"advancements":[7],"with":[8],"the":[9,37,79,91,158],"advent":[10],"of":[11,82,161],"deep":[12],"learning.":[13],"However,":[14,138],"their":[15,188],"performance":[16,160,184],"often":[17],"degrades":[18],"in":[19,25,39,68,108,117,134,191],"diverse":[20],"scenarios,":[21,94],"such":[22],"as":[23,66],"variations":[24],"viewing":[26],"angles,":[27],"lighting":[28],"conditions,":[29],"and":[30,46,73,104,125,132,150,185],"environmental":[31],"changes.":[32],"These":[33],"limitations":[34],"arise":[35],"from":[36],"difficulty":[38],"generalizing":[40],"across":[41,153],"multiple":[42],"factors,":[43],"including":[44,95],"environments":[45],"subject":[47],"appearances.":[48],"Multimodal":[49],"Large":[50],"Language":[51],"Models":[52],"(MLLMs)":[53],"offer":[54],"a":[55],"promising":[56,189],"alternative":[57],"to":[58,182],"address":[59],"these":[60],"challenges":[61],"by":[62,84,166],"leveraging":[63],"generalized":[64],"knowledge,":[65],"demonstrated":[67],"biometric":[69],"tasks":[70],"like":[71],"face":[72],"iris":[74],"recognition.":[75],"This":[76],"study":[77],"explores":[78],"Re-ID":[80,136,159,180],"capabilities":[81],"MLLMs":[83,89,116,162,178],"comparatively":[85],"evaluating":[86],"six":[87],"representative":[88],"on":[90],"most":[92],"challenging":[93,135],"angle":[96,119],"variation,":[97,120,147],"illumination":[98,121,146],"differences,":[99,122],"clothing":[100],"changes,":[101],"image":[102],"corruption,":[103],"visually":[105],"fine-grained":[106,126,151],"scenarios":[107],"Re-ID.":[109],"We":[110],"find":[111],"that":[112],"GPT-4o":[113],"outperforms":[114],"other":[115],"handling":[118],"corruption":[123,148],"resistance,":[124],"detail":[127],"disturbances,":[128],"demonstrating":[129],"high":[130],"accuracy":[131],"robustness":[133,144],"scenarios.":[137],"further":[139],"optimization":[140],"is":[141],"required":[142],"for":[143,176],"against":[145],"handling,":[149],"identification":[152],"all":[154],"tested":[155],"MLLMs.":[156],"Additionally,":[157],"can":[163],"be":[164],"improved":[165],"applying":[167],"several":[168],"prompt":[169],"templates.":[170],"Our":[171],"research":[172],"suggests":[173],"potential":[174,190],"directions":[175],"integrating":[177],"into":[179],"systems":[181],"enhance":[183],"robustness,":[186],"underscoring":[187],"this":[192],"field.":[193]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}